mattbucci
/

Devstral-24B-AWQ

4-bit precision

Model card Files Files and versions

Devstral-24B-AWQ

Commit History

add quantization_config.ignore=['lm_head'] (downstream audit fix)

91382f5
verified

mattbucci commited on Apr 29

Vision tested and working

b68f4c9
verified

mattbucci commited on Apr 15

Add known limitations (vision status)

c4c56b9
verified

mattbucci commited on Apr 15

Add model card for Devstral-24B AWQ 4-bit

b456643
verified

mattbucci commited on Apr 15

Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4

df87209
verified

mattbucci commited on Apr 15

initial commit

ede57b5
verified

mattbucci commited on Apr 15